Dr Brian Sheil

Dr Brian Sheil studied Civil Engineering for his undergraduate degree at the University of Galway. He studied the behaviour of deep foundation systems for his PhD jointly between the University of Galway and the University of California, Berkeley. In 2014, Brian joined the University of Oxford as a postdoctoral researcher in experimental geotechnics, focused on industry-funded research projects and was subsequently promoted to departmental lecturer in geotechnical engineering in January 2017. He was awarded a Royal Academy of Engineering Research Fellowship (at Oxford) in March 2018. At the same time, he was also awarded a Junior Research Fellowship at St Catherine’s College. In 2022, he was awarded the title of Associate Professor. In September 2022, Brian moved to the University of Cambridge to take up the Laing O’Rourke Associate Professorship in Construction Engineering while holding a Visiting Fellowship at the University of Oxford. In 2024, he became director of the Centre for Smart Infrastructure and Construction (CSIC) at Cambridge and was recently awarded an EPSRC Open Fellowship for his work on ‘Digital Underground Construction’.

Brian has won three awards for commercialising outcomes from his research, and in 2024, he co-founded the tech startup “InfraMind” to develop AI solutions for infrastructure, where he serves as Chief Scientist. InfraMind has delivered the world’s first “digital inspector” for infrastructure, which is currently being trialled by major organisations such as National Highways, Network Rail and Transport for London.

Brian is an editor of the journal ‘Data-Centric Engineering’, is an Associate Editor for ‘Journal of Computing in Civil Engineering’ and is an editorial board member for both ‘Tunnelling & Underground Space Technology’ and ‘Underground Space’. He recently received the ‘Young Researcher Award 2022’ from the Civil Engineering Research Association of Ireland, the ‘Bright Spark Lecture Award’ from the International Society for Soil Mechanics and Geotechnical Engineering and the ‘Geotechnical Engineering Proceedings Lecture’ nominated by the Editorial Panel of ICE Proceedings Geotechnical Engineering.

Brian's research puts physics first in developing trustworthy AI for infrastructure. His team focuses on creating the next generation of digital twins for underground assets by fusing physics-informed learning, computer vision, multimodal sensing, and multi-scale simulation. His work spans particle-scale imaging and ground modelling through to asset-level inspection, early warning, and lifecycle management. Core areas include physics-informed neural networks/operators, data-efficient learning, computer vision, 3D point cloud and GPR analysis. Applications include tunnelling, basements, shafts, deep excavations, mining, deep foundations, and highway infrastructure. The overarching aim of his work is to transform the productivity, resilience, and sustainability of underground infrastructure delivery and maintenance. Specifically, the key themes Brian’s research covers include:

• Physics-first AI
• Computer vision for infrastructure
• Multi-scale, multi-fidelity simulation
• Intelligent sensing and imaging
• Data-centric digital twins
• Foundation models for infrastructure